To address the degradation of visual-language (VL) representations during VLA supervised fine-tuning (SFT), we introduce Visual Representation Alignment. During SFT, we pull a VLA’s visual tokens ...
CLIP is one of the most important multimodal foundational models today. What powers CLIP’s capabilities? The rich supervision signals provided by natural language, the carrier of human knowledge, ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback